Novel DLSNNC and SBS based framework for improving QoS in healthcare-IoT applications

Abstract

Health care system is intended to enhance one's health and as a result, one's quality of life. In order to fulfil its social commitment, health care must focus on producing social profit to sustain itself. Also, due to ever increasing demand of healthcare sector, there is drastic rise in the amount of patient data that is produced and needs to be stored for long duration for clinical reference. The risk of patient data being lost due to a data centre failure can be minimized by including a fog layer into the cloud computing architecture. Furthermore, the burden of such data produced is stored on the cloud. In order to increase service quality, we introduce fog computing based on deep learning sigmoid-based neural network clustering (DLSNNC) and score-based scheduling (SBS). Fog computing begins by collecting and storing healthcare data on the cloud layer, using data collected through sensors. Deep learning sigmoid based neural network clustering and score based Scheduling approaches are used to determine entropy for each fog node in the fog layer. Sensors collect data and send it to the fog layer, while the cloud computing tier is responsible for monitoring the healthcare system. The exploratory findings show promising results in terms of end-to-end latency and network utilization. Also, the proposed system outperforms the existing techniques in terms of average delay.